Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 16k
    5. 0-GEMMASCOPE-MLP-16K
    6. 62
    Prev
    Next
    INDEX
    Explanations

    programming elements, specifically related to data types and error handling in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical terms and symbols commonly used in programming and data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.74
    CppCodeGen
    -0.70
     Cea
    -0.62
     betweenstory
    -0.59
     Waray
    -0.57
    iastes
    -0.57
     <>",
    -0.55
    DATABASES
    -0.54
    Filmographie
    -0.54
    windowFixed
    -0.54
    POSITIVE LOGITS
     coû
    0.53
     الاطلاع
    0.53
    ]++;
    0.52
    ]){
    
    0.50
    prova
    0.48
    écnicas
    0.48
    getMenuInflater
    0.47
     ruok
    0.47
    uestamente
    0.47
    ıntı
    0.46
    Activations Density 0.800%

    No Known Activations